nttx commited on
Commit
fb3fc1a
·
verified ·
1 Parent(s): 1979ae9

Training in progress, step 100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef831837ab0cac05dbea5415796eb5aecad7dde8a3f34db8a3e2cc4df9669bec
3
  size 60010048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51cc9f8030334bdb6572244c6c1a9ea917de11f21d2595490578cda88ec35775
3
  size 60010048
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e33f22e8541fb33ddaa5cd2472327062fa75216960c88f61b3e24b8ee9670d90
3
  size 120213058
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79652339a28c00946d20729dfdf82ff45d25fe4652db4c30e04340773fd57fa4
3
  size 120213058
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:faaa1f69fc005a5e74ee66ee7f4a760e41a9a1cb46362b506ce589df0b143e2e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8933670821aabb3070d0173fb41e6271908e860b8c408e6e3b33d78b9e9127e8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1900bd8021f13c38b942ed30aea6e2cea1b47664e4ce28d0276b142334732307
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.5381035804748535,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.9029345372460497,
5
  "eval_steps": 50,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -373,6 +373,364 @@
373
  "eval_samples_per_second": 18.611,
374
  "eval_steps_per_second": 4.752,
375
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
376
  }
377
  ],
378
  "logging_steps": 1,
@@ -396,12 +754,12 @@
396
  "should_evaluate": false,
397
  "should_log": false,
398
  "should_save": true,
399
- "should_training_stop": false
400
  },
401
  "attributes": {}
402
  }
403
  },
404
- "total_flos": 2.733718696152269e+16,
405
  "train_batch_size": 4,
406
  "trial_name": null,
407
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.526015281677246,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 1.8081264108352144,
5
  "eval_steps": 50,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
373
  "eval_samples_per_second": 18.611,
374
  "eval_steps_per_second": 4.752,
375
  "step": 50
376
+ },
377
+ {
378
+ "epoch": 0.9209932279909706,
379
+ "grad_norm": 0.21468926966190338,
380
+ "learning_rate": 2.847932752400164e-06,
381
+ "loss": 2.4698,
382
+ "step": 51
383
+ },
384
+ {
385
+ "epoch": 0.9390519187358917,
386
+ "grad_norm": 0.27597546577453613,
387
+ "learning_rate": 2.761321158169134e-06,
388
+ "loss": 2.5527,
389
+ "step": 52
390
+ },
391
+ {
392
+ "epoch": 0.9571106094808126,
393
+ "grad_norm": 0.18966849148273468,
394
+ "learning_rate": 2.6743911843603134e-06,
395
+ "loss": 2.4706,
396
+ "step": 53
397
+ },
398
+ {
399
+ "epoch": 0.9751693002257337,
400
+ "grad_norm": 0.1804044097661972,
401
+ "learning_rate": 2.587248741756253e-06,
402
+ "loss": 2.4602,
403
+ "step": 54
404
+ },
405
+ {
406
+ "epoch": 0.9932279909706546,
407
+ "grad_norm": 0.20892418920993805,
408
+ "learning_rate": 2.5e-06,
409
+ "loss": 2.4807,
410
+ "step": 55
411
+ },
412
+ {
413
+ "epoch": 1.0135440180586908,
414
+ "grad_norm": 0.4648563265800476,
415
+ "learning_rate": 2.4127512582437486e-06,
416
+ "loss": 4.1884,
417
+ "step": 56
418
+ },
419
+ {
420
+ "epoch": 1.0316027088036117,
421
+ "grad_norm": 0.1795751303434372,
422
+ "learning_rate": 2.325608815639687e-06,
423
+ "loss": 2.3664,
424
+ "step": 57
425
+ },
426
+ {
427
+ "epoch": 1.0496613995485327,
428
+ "grad_norm": 0.17576627433300018,
429
+ "learning_rate": 2.238678841830867e-06,
430
+ "loss": 2.4723,
431
+ "step": 58
432
+ },
433
+ {
434
+ "epoch": 1.0677200902934538,
435
+ "grad_norm": 0.17835436761379242,
436
+ "learning_rate": 2.1520672475998374e-06,
437
+ "loss": 2.4349,
438
+ "step": 59
439
+ },
440
+ {
441
+ "epoch": 1.0857787810383748,
442
+ "grad_norm": 0.18056568503379822,
443
+ "learning_rate": 2.0658795558326745e-06,
444
+ "loss": 2.4368,
445
+ "step": 60
446
+ },
447
+ {
448
+ "epoch": 1.1038374717832957,
449
+ "grad_norm": 0.18356956541538239,
450
+ "learning_rate": 1.9802207729556023e-06,
451
+ "loss": 2.5736,
452
+ "step": 61
453
+ },
454
+ {
455
+ "epoch": 1.1218961625282167,
456
+ "grad_norm": 0.1716766059398651,
457
+ "learning_rate": 1.895195261000831e-06,
458
+ "loss": 2.4208,
459
+ "step": 62
460
+ },
461
+ {
462
+ "epoch": 1.1399548532731376,
463
+ "grad_norm": 0.1821490377187729,
464
+ "learning_rate": 1.8109066104575023e-06,
465
+ "loss": 2.582,
466
+ "step": 63
467
+ },
468
+ {
469
+ "epoch": 1.1580135440180588,
470
+ "grad_norm": 0.18071655929088593,
471
+ "learning_rate": 1.7274575140626318e-06,
472
+ "loss": 2.5713,
473
+ "step": 64
474
+ },
475
+ {
476
+ "epoch": 1.1760722347629797,
477
+ "grad_norm": 0.18022793531417847,
478
+ "learning_rate": 1.6449496416858285e-06,
479
+ "loss": 2.5023,
480
+ "step": 65
481
+ },
482
+ {
483
+ "epoch": 1.1941309255079007,
484
+ "grad_norm": 0.19963014125823975,
485
+ "learning_rate": 1.56348351646022e-06,
486
+ "loss": 2.2639,
487
+ "step": 66
488
+ },
489
+ {
490
+ "epoch": 1.2121896162528216,
491
+ "grad_norm": 0.235209122300148,
492
+ "learning_rate": 1.4831583923105e-06,
493
+ "loss": 2.5076,
494
+ "step": 67
495
+ },
496
+ {
497
+ "epoch": 1.2302483069977426,
498
+ "grad_norm": 0.2917708158493042,
499
+ "learning_rate": 1.4040721330273063e-06,
500
+ "loss": 2.4368,
501
+ "step": 68
502
+ },
503
+ {
504
+ "epoch": 1.2483069977426637,
505
+ "grad_norm": 0.1890561729669571,
506
+ "learning_rate": 1.3263210930352737e-06,
507
+ "loss": 2.313,
508
+ "step": 69
509
+ },
510
+ {
511
+ "epoch": 1.2663656884875847,
512
+ "grad_norm": 0.2030169516801834,
513
+ "learning_rate": 1.2500000000000007e-06,
514
+ "loss": 2.5029,
515
+ "step": 70
516
+ },
517
+ {
518
+ "epoch": 1.2844243792325056,
519
+ "grad_norm": 0.1738690584897995,
520
+ "learning_rate": 1.1752018394169882e-06,
521
+ "loss": 2.4346,
522
+ "step": 71
523
+ },
524
+ {
525
+ "epoch": 1.3024830699774266,
526
+ "grad_norm": 0.18556749820709229,
527
+ "learning_rate": 1.1020177413231334e-06,
528
+ "loss": 2.4441,
529
+ "step": 72
530
+ },
531
+ {
532
+ "epoch": 1.3205417607223477,
533
+ "grad_norm": 0.1627313792705536,
534
+ "learning_rate": 1.0305368692688175e-06,
535
+ "loss": 2.5455,
536
+ "step": 73
537
+ },
538
+ {
539
+ "epoch": 1.3386004514672687,
540
+ "grad_norm": 0.16638238728046417,
541
+ "learning_rate": 9.608463116858544e-07,
542
+ "loss": 2.4389,
543
+ "step": 74
544
+ },
545
+ {
546
+ "epoch": 1.3566591422121896,
547
+ "grad_norm": 0.17029760777950287,
548
+ "learning_rate": 8.930309757836517e-07,
549
+ "loss": 2.5624,
550
+ "step": 75
551
+ },
552
+ {
553
+ "epoch": 1.3747178329571106,
554
+ "grad_norm": 0.1706266552209854,
555
+ "learning_rate": 8.271734841028553e-07,
556
+ "loss": 2.6277,
557
+ "step": 76
558
+ },
559
+ {
560
+ "epoch": 1.3927765237020315,
561
+ "grad_norm": 0.1721290498971939,
562
+ "learning_rate": 7.633540738525066e-07,
563
+ "loss": 2.5122,
564
+ "step": 77
565
+ },
566
+ {
567
+ "epoch": 1.4108352144469527,
568
+ "grad_norm": 0.1745157390832901,
569
+ "learning_rate": 7.016504991533727e-07,
570
+ "loss": 2.565,
571
+ "step": 78
572
+ },
573
+ {
574
+ "epoch": 1.4288939051918736,
575
+ "grad_norm": 0.20027202367782593,
576
+ "learning_rate": 6.421379363065142e-07,
577
+ "loss": 2.396,
578
+ "step": 79
579
+ },
580
+ {
581
+ "epoch": 1.4469525959367946,
582
+ "grad_norm": 0.20897327363491058,
583
+ "learning_rate": 5.848888922025553e-07,
584
+ "loss": 2.4836,
585
+ "step": 80
586
+ },
587
+ {
588
+ "epoch": 1.4650112866817155,
589
+ "grad_norm": 0.2554313540458679,
590
+ "learning_rate": 5.299731159831953e-07,
591
+ "loss": 2.647,
592
+ "step": 81
593
+ },
594
+ {
595
+ "epoch": 1.4830699774266365,
596
+ "grad_norm": 0.1745099127292633,
597
+ "learning_rate": 4.774575140626317e-07,
598
+ "loss": 2.2255,
599
+ "step": 82
600
+ },
601
+ {
602
+ "epoch": 1.5011286681715577,
603
+ "grad_norm": 0.17403315007686615,
604
+ "learning_rate": 4.27406068612396e-07,
605
+ "loss": 2.3811,
606
+ "step": 83
607
+ },
608
+ {
609
+ "epoch": 1.5191873589164786,
610
+ "grad_norm": 0.17667503654956818,
611
+ "learning_rate": 3.798797596089351e-07,
612
+ "loss": 2.4181,
613
+ "step": 84
614
+ },
615
+ {
616
+ "epoch": 1.5372460496613995,
617
+ "grad_norm": 0.16373108327388763,
618
+ "learning_rate": 3.3493649053890325e-07,
619
+ "loss": 2.4125,
620
+ "step": 85
621
+ },
622
+ {
623
+ "epoch": 1.5553047404063205,
624
+ "grad_norm": 0.17596249282360077,
625
+ "learning_rate": 2.9263101785268253e-07,
626
+ "loss": 2.578,
627
+ "step": 86
628
+ },
629
+ {
630
+ "epoch": 1.5733634311512414,
631
+ "grad_norm": 0.17639108002185822,
632
+ "learning_rate": 2.53014884252083e-07,
633
+ "loss": 2.5718,
634
+ "step": 87
635
+ },
636
+ {
637
+ "epoch": 1.5914221218961626,
638
+ "grad_norm": 0.17920009791851044,
639
+ "learning_rate": 2.1613635589349756e-07,
640
+ "loss": 2.3993,
641
+ "step": 88
642
+ },
643
+ {
644
+ "epoch": 1.6094808126410836,
645
+ "grad_norm": 0.1696009337902069,
646
+ "learning_rate": 1.8204036358303173e-07,
647
+ "loss": 2.5044,
648
+ "step": 89
649
+ },
650
+ {
651
+ "epoch": 1.6275395033860045,
652
+ "grad_norm": 0.16778811812400818,
653
+ "learning_rate": 1.507684480352292e-07,
654
+ "loss": 2.5485,
655
+ "step": 90
656
+ },
657
+ {
658
+ "epoch": 1.6455981941309257,
659
+ "grad_norm": 0.16828463971614838,
660
+ "learning_rate": 1.223587092621162e-07,
661
+ "loss": 2.6222,
662
+ "step": 91
663
+ },
664
+ {
665
+ "epoch": 1.6636568848758464,
666
+ "grad_norm": 0.2024766057729721,
667
+ "learning_rate": 9.684576015420277e-08,
668
+ "loss": 2.4161,
669
+ "step": 92
670
+ },
671
+ {
672
+ "epoch": 1.6817155756207676,
673
+ "grad_norm": 0.21227002143859863,
674
+ "learning_rate": 7.426068431000883e-08,
675
+ "loss": 2.5339,
676
+ "step": 93
677
+ },
678
+ {
679
+ "epoch": 1.6997742663656885,
680
+ "grad_norm": 0.25471073389053345,
681
+ "learning_rate": 5.463099816548578e-08,
682
+ "loss": 2.7598,
683
+ "step": 94
684
+ },
685
+ {
686
+ "epoch": 1.7178329571106095,
687
+ "grad_norm": 0.17452920973300934,
688
+ "learning_rate": 3.798061746947995e-08,
689
+ "loss": 2.2005,
690
+ "step": 95
691
+ },
692
+ {
693
+ "epoch": 1.7358916478555306,
694
+ "grad_norm": 0.17418447136878967,
695
+ "learning_rate": 2.4329828146074096e-08,
696
+ "loss": 2.4726,
697
+ "step": 96
698
+ },
699
+ {
700
+ "epoch": 1.7539503386004514,
701
+ "grad_norm": 0.17382381856441498,
702
+ "learning_rate": 1.3695261579316776e-08,
703
+ "loss": 2.5143,
704
+ "step": 97
705
+ },
706
+ {
707
+ "epoch": 1.7720090293453725,
708
+ "grad_norm": 0.18013960123062134,
709
+ "learning_rate": 6.089874350439507e-09,
710
+ "loss": 2.536,
711
+ "step": 98
712
+ },
713
+ {
714
+ "epoch": 1.7900677200902935,
715
+ "grad_norm": 0.17495931684970856,
716
+ "learning_rate": 1.5229324522605949e-09,
717
+ "loss": 2.5295,
718
+ "step": 99
719
+ },
720
+ {
721
+ "epoch": 1.8081264108352144,
722
+ "grad_norm": 0.16573888063430786,
723
+ "learning_rate": 0.0,
724
+ "loss": 2.5161,
725
+ "step": 100
726
+ },
727
+ {
728
+ "epoch": 1.8081264108352144,
729
+ "eval_loss": 2.526015281677246,
730
+ "eval_runtime": 4.9445,
731
+ "eval_samples_per_second": 19.011,
732
+ "eval_steps_per_second": 4.854,
733
+ "step": 100
734
  }
735
  ],
736
  "logging_steps": 1,
 
754
  "should_evaluate": false,
755
  "should_log": false,
756
  "should_save": true,
757
+ "should_training_stop": true
758
  },
759
  "attributes": {}
760
  }
761
  },
762
+ "total_flos": 5.39928374059991e+16,
763
  "train_batch_size": 4,
764
  "trial_name": null,
765
  "trial_params": null